Contrastive Syn-to-Real Generalization

Abstract

Training on synthetic data can be beneficial for label or data-scarce scenarios. However, synthetically trained models often suffer from poor generalization in real domains due to domain gaps. In this work, we make a key observation that the diversity of the learned feature embeddings plays an important role in the generalization performance. To this end, we propose contrastive synthetic-to-real generalization (CSG), a novel framework that leverages the pre-trained ImageNet knowledge to prevent overfitting to the synthetic domain, while promoting the diversity of feature embeddings as an inductive bias to improve generalization. In addition, we enhance the proposed CSG framework with attentional pooling (A-pool) to let the model focus on semantically important regions and further improve its generalization. We demonstrate the effectiveness of CSG on various synthetic training tasks, exhibiting state-of-the-art performance on zero-shot domain generalization.

Accepted in ICLR 2021

References in corpus (12)

• Overcoming catastrophic forgetting in neural networks
• Rethinking Atrous Convolution for Semantic Image Segmentation
• A Simple Framework for Contrastive Learning of Visual Representations
• Improved Baselines with Momentum Contrastive Learning
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Continual Learning Through Synaptic Intelligence
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness
• Domain Generalization via Invariant Feature Representation
• VisDA: The Visual Domain Adaptation Challenge
• Contrastive Multiview Coding
• Automated Synthetic-to-Real Generalization